© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7830
    Prev
    Next
    INDEX
    Explanations

    suggesting or explaining

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¦ĸåıij
    -0.10
    æĤ¼
    -0.09
    echa
    -0.09
    æıı
    -0.09
    æĺİç¡®è§Ħå®ļ
    -0.09
    æłĩæĺİ
    -0.09
     NOI
    -0.08
    inf
    -0.08
    å½³
    -0.08
    åĢ©
    -0.08
    POSITIVE LOGITS
    建议
    0.15
    åĬĿ
    0.12
    建èŃ°
    0.12
    å¼ķ导
    0.11
     Suggestions
    0.10
     suggestions
    0.10
     gợi
    0.10
    ãģĬåĭ§ãĤģ
    0.10
    æݨèįIJ
    0.10
    çģĮ
    0.10
    Activations Density 0.256%

    No Known Activations